Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1310
    Prev
    Next
    INDEX
    Explanations

    natural disasters, medical conditions, and substances

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    480
    +0.37
    2.0%
    447
    +0.30
    1.6%
    481
    +0.23
    1.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.37
    0.20
    480
    +0.30
    0.07
    464
    +0.23
    0.20
    Negative Logits
    Ire
    -0.69
     Vaugh
    -0.60
    ãĥ¼ãĥĨ
    -0.58
     Peb
    -0.58
     Niet
    -0.56
    é¾įå
    -0.55
    omever
    -0.55
    eday
    -0.55
     Instr
    -0.54
     agre
    -0.53
    POSITIVE LOGITS
    ¶
    0.63
     âĵĺ
    0.63
     welcomes
    0.57
     âĢº
    0.56
     reacts
    0.53
     ·
    0.52
     overview
    0.52
     greets
    0.51
     |
    0.51
     ]
    0.50
    Activations Density 4.047%

    No Known Activations